Adaptive MCMC methods with applications in environmental and geophysical models

This work presents new, efficient Markov chain Monte Carlo (MCMC) simulation methods for statistical analysis in various modelling applications. When using MCMC methods, the model is simulated repeatedly to explore the probability distribution describing the uncertainties in model parameters and predictions. In adaptive MCMC methods based on the Metropolis-Hastings algorithm, the proposal distribution needed by the algorithm learns from the target distribution as the simulation proceeds. Adaptive MCMC methods have been subject of intensive research lately, as they open a way for essentially easier use of the methodology. The lack of user-friendly computer programs has been a main obstacle for wider acceptance of the methods. This work provides two new adaptive MCMC methods: DRAM and AARJ. The DRAM method has been built especially to work in high dimensional and non-linear problems. The AARJ method is an extension to DRAM for model selection problems, where the mathematical formulation of the model is uncertain and we want simultaneously to fit several different models to the same observations. The methods were developed while keeping in mind the needs of modelling applications typical in environmental sciences. The development work has been pursued while working with several application projects. The applications presented in this work are: a winter time oxygen concentration model for Lake Tuusulanjärvi and adaptive control of the aerator; a nutrition model for Lake Pyhäjärvi and lake management planning; validation of the algorithms of the GOMOS ozone remote sensing instrument on board the Envisat satellite of European Space Agency and the study of the effects of aerosol model selection on the GOMOS algorithm.

Characterization of hepatic fatty acids in mice with reduced liver fat by ultra-short echo time (1)H-MRS at 14.1 T in vivo.

Alterations in the hepatic lipid content (HLC) and fatty acid composition are associated with disruptions in whole body metabolism, both in humans and in rodent models, and can be non-invasively assessed by (1)H-MRS in vivo. We used (1)H-MRS to characterize the hepatic fatty-acyl chains of healthy mice and to follow changes caused by streptozotocin (STZ) injection. Using STEAM at 14.1 T with an ultra-short TE of 2.8 ms, confounding effects from T2 relaxation and J-coupling were avoided, allowing for accurate estimations of the contribution of unsaturated (UFA), saturated (SFA), mono-unsaturated (MUFA) and poly-unsaturated (PUFA) fatty-acyl chains, number of double bonds, PU bonds and mean chain length. Compared with in vivo (1) H-MRS, high resolution NMR performed in vitro in hepatic lipid extracts reported longer fatty-acyl chains (18 versus 15 carbons) with a lower contribution from UFA (61 ± 1% versus 80 ± 5%) but a higher number of PU bonds per UFA (1.39 ± 0.03 versus 0.58 ± 0.08), driven by the presence of membrane species in the extracts. STZ injection caused a decrease of HLC (from 1.7 ± 0.3% to 0.7 ± 0.1%), an increase in the contribution of SFA (from 21 ± 2% to 45 ± 6%) and a reduction of the mean length (from 15 to 13 carbons) of cytosolic fatty-acyl chains. In addition, SFAs were also likely to have increased in membrane lipids of STZ-induced diabetic mice, along with a decrease of the mean chain length. These studies show the applicability of (1)H-MRS in vivo to monitor changes in the composition of the hepatic fatty-acyl chains in mice even when they exhibit reduced HLC, pointing to the value of this methodology to evaluate lipid-lowering interventions in the scope of metabolic disorders.

The Psychometric Properties of the French Version of the Personality Inventory for DSM-5.

In the context of the publication of DSM-5, the Personality Inventory for DSM-5 (PID-5) has been proposed as a new dimensional assessment tool for personality disorders. This instrument includes a pool of 220 items organized around 25 facets included in a five-factor second-order domain structure. The examination of the replicability of the trait structure across methods and populations is of primary importance. In view of this need, the main objective of the current study was to validate the French version of the PID-5 among French-speaking adults from a European community sample (N=2,532). In particular, the assumption of unidimensionality of the 25 facet and the five domain scales was tested, as well as the extent to which the five-factor structure of the PID-5 and the DSM-5 personality trait hierarchical structure are replicated in the current sample. The results support the assumption of unidimensionality of both the facets and the domains. Exploratory factor and hierarchical analyses replicated the five-factor structure as initially proposed in the PID-5.

Unifying Time to Contact Estimation and Collision Avoidance across Species

The -function and the -function are phenomenological models that are widely used in the context of timing interceptive actions and collision avoidance, respectively. Both models were previously considered to be unrelated to each other: is a decreasing function that provides an estimation of time-to-contact (ttc) in the early phase of an object approach; in contrast, has a maximum before ttc. Furthermore, it is not clear how both functions could be implemented at the neuronal level in a biophysically plausible fashion. Here we propose a new framework- the corrected modified Tau function- capable of predicting both -type ("") and -type ("") responses. The outstanding property of our new framework is its resilience to noise. We show that can be derived from a firing rate equation, and, as , serves to describe the response curves of collision sensitive neurons. Furthermore, we show that predicts the psychophysical performance of subjects determining ttc. Our new framework is thus validated successfully against published and novel experimental data. Within the framework, links between -type and -type neurons are established. Therefore, it could possibly serve as a model for explaining the co-occurrence of such neurons in the brain.

Classification models for neurocognitive impairment in HIV infection based on demographic and clinical variables

Objective: We used demographic and clinical data to design practical classification models for prediction of neurocognitive impairment (NCI) in people with HIV infection. Methods: The study population comprised 331 HIV-infected patients with available demographic, clinical, and neurocognitive data collected using a comprehensive battery of neuropsychological tests. Classification and regression trees (CART) were developed to btain detailed and reliable models to predict NCI. Following a practical clinical approach, NCI was considered the main variable for study outcomes, and analyses were performed separately in treatment-naïve and treatment-experienced patients. Results: The study sample comprised 52 treatment-naïve and 279 experienced patients. In the first group, the variables identified as better predictors of NCI were CD4 cell count and age (correct classification [CC]: 79.6%, 3 final nodes). In treatment-experienced patients, the variables most closely related to NCI were years of education, nadir CD4 cell count, central nervous system penetration-effectiveness score, age, employment status, and confounding comorbidities (CC: 82.1%, 7 final nodes). In patients with an undetectable viral load and no comorbidities, we obtained a fairly accurate model in which the main variables were nadir CD4 cell count, current CD4 cell count, time on current treatment, and past highest viral load (CC: 88%, 6 final nodes). Conclusion: Practical classification models to predict NCI in HIV infection can be obtained using demographic and clinical variables. An approach based on CART analyses may facilitate screening for HIV-associated neurocognitive disorders and complement clinical information about risk and protective factors for NCI in HIV-infected patients.

Reframing video gaming and internet use addiction : empirical cross-national comparison of heavy use over time and addiction scales among young users

BACKGROUND AND AIMS: Evidence-based and reliable measures of addictive disorders are needed in general population-based assessments. One study suggested that heavy use over time (UOT) should be used instead of self-reported addiction scales (AS). This study compared UOT and AS regarding video gaming and internet use empirically, using associations with comorbid factors. DESIGN: Cross-sectional data from the 2011 French Survey on Health and Consumption on Call-up and Preparation for Defence-Day (ESCAPAD), cross-sectional data from the 2012 Swiss ado@internet.ch study and two waves of longitudinal data (2010-13) of the Swiss Longitudinal Cohort Study on Substance Use Risk Factors (C-SURF). SETTING: Three representative samples from the general population of French and Swiss adolescents and young Swiss men, aged approximately 17, 14 and 20 years, respectively. PARTICIPANTS: ESCAPAD: n =22 945 (47.4% men); ado@internet.ch: n =3049 (50% men); C-SURF: n =4813 (baseline + follow-up, 100% men). MEASUREMENTS: We assessed video gaming/internet UOT ESCAPAD and ado@internet.ch: number of hours spent online per week, C-SURF: latent score of time spent gaming/using internet] and AS (ESCAPAD: Problematic Internet Use Questionnaire, ado@internet.ch: Internet Addiction Test, C-SURF: Gaming AS). Comorbidities were assessed with health outcomes (ESCAPAD: physical health evaluation with a single item, suicidal thoughts, and appointment with a psychiatrist; ado@internet.ch: WHO-5 and somatic health problems; C-SURF: Short Form 12 (SF-12 Health Survey) and Major Depression Inventory (MDI). FINDINGS: UOT and AS were correlated moderately (ESCAPAD: r = 0.40, ado@internet.ch: r = 0.53 and C-SURF: r = 0.51). Associations of AS with comorbidity factors were higher than those of UOT in cross-sectional (AS: .005 ≤ |b| ≤ 2.500, UOT: 0.001 ≤ |b| ≤ 1.000) and longitudinal analyses (AS: 0.093 ≤ |b| ≤ 1.079, UOT: 0.020 ≤ |b| ≤ 0.329). The results were similar across gender in ESCAPAD and ado@internet.ch (men: AS: 0.006 ≤ |b| ≤ 0.211, UOT: 0.001 ≤ |b| ≤ 0.061; women: AS: 0.004 ≤ |b| ≤ 0.155, UOT: 0.001 ≤ |b| ≤ 0.094). CONCLUSIONS: The measurement of heavy use over time captures part of addictive video gaming/internet use without overlapping to a large extent with the results of measuring by self-reported addiction scales (AS). Measuring addictive video gaming/internet use via self-reported addiction scales relates more strongly to comorbidity factors than heavy use over time.

Courts and Courtly Cultures in Early Modern Italy and Europe: Models and Languages

This volume deals with the forms of propaganda and self-representation, through words and images, during the rise of the 'civiltà delle corti' and through processes typical of the time, such as confrontation, adaptation, competition and rivalry. This period, which marked the passage of Italian and European culture from the Middle Ages to the Renaissance, is fundamental in the development of Modern Europe, and it lasted up to the XVIII century and beyond. At the heart of many matters debated here lies the relationship between culture and politics. The formation of a 'Lombard identity', central to the Sinergia project which was the frame of the whole research and its conferences, is closely linked to this broad general context. It places the so called 'questione milanese' - above the traditional hierarchies 'Toscana oriented' - at the centre of many questions regarding Northern Italy as a whole, starting from the dissolution of the Medieval communes, through to the rise of the signorie, from the end of the XIII century and the beginning of the XIV century up to the early XVI century.

Time-varying Risk Premiums and Conditional Market Risk: Empirical Evidence from European Stock Markets

This study investigates the relationship between the time-varying risk premiums and conditional market risk in the stock markets of the ten member countries of Economy and Monetary Union. Second, it examines whether the conditional second moments change over time and are there asymmetric effects in the conditional covariance matrix. Third, it analyzes the possible effects of the chosen testing framework. Empirical analysis is conducted using asymmetric univariate and multivariate GARCH-in-mean models and assuming three different degrees of market integration. For a daily sample period from 1999 to 2007, the study shows that the time-varying market risk alone is not enough to explain the dynamics of risk premiums and indications are found that the market risk is detected only when its price is allowed to change over time. Also asymmetric effects in the conditional covariance matrix, which is found to be time-varying, are clearly present and should be recognized in empirical asset pricing analyses.

Tests of International Asset Pricing Models in Scandinavian Stock Markets

This thesis examines whether global, local and exchange risks are priced in Scandinavian countries’ equity markets by using conditional international asset pricing models. The employed international asset pricing models are the world capital asset pricing model, the international asset pricing model augmented with the currency risk, and the partially segmented model augmented with the currency risk. Moreover, this research traces estimated equity risk premiums for the Scandinavian countries. The empirical part of the study is performed using generalized method of moments approach. Monthly observations from February 1994 to June 2007 are used. Investors’ conditional expectations are modeled using several instrumental variables. In order to keep system parsimonious the prices of risk are assumed to be constant whereas expected returns and conditional covariances vary over time. The empirical findings of this thesis suggest that the prices of global and local market risk are priced in the Scandinavian countries. This indicates that the Scandinavian countries are mildly segmented from the global markets. Furthermore, the results show that the exchange risk is priced in the Danish and Swedish stock markets when the partially segmented model is augmented with the currency risk factor.

Statistical Analysis and Numerics of Heat Exchanger Models

The identifiability of the parameters of a heat exchanger model without phase change was studied in this Master’s thesis using synthetically made data. A fast, two-step Markov chain Monte Carlo method (MCMC) was tested with a couple of case studies and a heat exchanger model. The two-step MCMC-method worked well and decreased the computation time compared to the traditional MCMC-method. The effect of measurement accuracy of certain control variables to the identifiability of parameters was also studied. The accuracy used did not seem to have a remarkable effect to the identifiability of parameters. The use of the posterior distribution of parameters in different heat exchanger geometries was studied. It would be computationally most efficient to use the same posterior distribution among different geometries in the optimisation of heat exchanger networks. According to the results, this was possible in the case when the frontal surface areas were the same among different geometries. In the other cases the same posterior distribution can be used for optimisation too, but that will give a wider predictive distribution as a result. For condensing surface heat exchangers the numerical stability of the simulation model was studied. As a result, a stable algorithm was developed.

Fronts with continuous waiting-time distributions: Theory and application to virus infections

We generalize to arbitrary waiting-time distributions some results which were previously derived for discrete distributions. We show that for any two waiting-time distributions with the same mean delay time, that with higher dispersion will lead to a faster front. Experimental data on the speed of virus infections in a plaque are correctly explained by the theoretical predictions using a Gaussian delay-time distribution, which is more realistic for this system than the Dirac delta distribution considered previously [J. Fort and V. Méndez, Phys. Rev. Lett.89, 178101 (2002)]

The Role of the Delay Time in the Modeling of Biological Range Expansions

The time interval between successive migrations of biological species causes a delay time in the reaction-diffusion equations describing their space-time dynamics. This lowers the predicted speed of the waves of advance, as compared to classical models. It has been shown that this delay-time effect improves the modeling of human range expansions. Here, we demonstrate that it can also be important for other species. We present two new examples where the predictions of the time-delayed and the classical (Fisher) approaches are compared to experimental data. No free or adjustable parameters are used. We show that the importance of the delay effect depends on the dimensionless product of the initial growth rate and the delay time. We argue that the delay effect should be taken into account in the modeling of range expansions for biological species

Time-Delayed Spread of Viruses in Growing Plaques

The spread of viruses in growing plaques predicted by classical models is greater than that measured experimentally. There is a widespread belief that this discrepancy is due to biological factors. Here we show that the observed speeds can be satisfactorily predicted by a purely physical model that takes into account the delay time due to virus reproduction inside infected cells. No free or adjustable parameters are used

Analysis of patterns in mining time series using Qlucore

Raw measurement data does not always immediately convey useful information, but applying mathematical statistical analysis tools into measurement data can improve the situation. Data analysis can offer benefits like acquiring meaningful insight from the dataset, basing critical decisions on the findings, and ruling out human bias through proper statistical treatment. In this thesis we analyze data from an industrial mineral processing plant with the aim of studying the possibility of forecasting the quality of the final product, given by one variable, with a model based on the other variables. For the study mathematical tools like Qlucore Omics Explorer (QOE) and Sparse Bayesian regression (SB) are used. Later on, linear regression is used to build a model based on a subset of variables that seem to have most significant weights in the SB model. The results obtained from QOE show that the variable representing the desired final product does not correlate with other variables. For SB and linear regression, the results show that both SB and linear regression models built on 1-day averaged data seriously underestimate the variance of true data, whereas the two models built on 1-month averaged data are reliable and able to explain a larger proportion of variability in the available data, making them suitable for prediction purposes. However, it is concluded that no single model can fit well the whole available dataset and therefore, it is proposed for future work to make piecewise non linear regression models if the same available dataset is used, or the plant to provide another dataset that should be collected in a more systematic fashion than the present data for further analysis.

MCMC Analysis Of Classical Time Series Algorithms

Identification of order of an Autoregressive Moving Average Model (ARMA) by the usual graphical method is subjective. Hence, there is a need of developing a technique to identify the order without employing the graphical investigation of series autocorrelations. To avoid subjectivity, this thesis focuses on determining the order of the Autoregressive Moving Average Model using Reversible Jump Markov Chain Monte Carlo (RJMCMC). The RJMCMC selects the model from a set of the models suggested by better fitting, standard deviation errors and the frequency of accepted data. Together with deep analysis of the classical Box-Jenkins modeling methodology the integration with MCMC algorithms has been focused through parameter estimation and model fitting of ARMA models. This helps to verify how well the MCMC algorithms can treat the ARMA models, by comparing the results with graphical method. It has been seen that the MCMC produced better results than the classical time series approach.